He, Jie, Chi Lok U, Simon, Gutierrez Basulto, Victor  ORCID: https://orcid.org/0000-0002-6117-5459 and Pan, Jeff Z.
2023.
BUCA: A binary classification approach to unsupervised commonsense question answering.
Presented at: 61st Annual Meeting of the Association for Computational Linguistics (ACL?23),
Toronto, Canada,
9-14 July 2023.
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics.
, vol.2
ACL,
pp. 376-387.
10.18653/v1/2023.acl-short.33
|
Preview |
PDF
- Accepted Post-Print Version
Download (543kB) | Preview |
Abstract
Unsupervised commonsense reasoning (UCR) is becoming increasingly popular as the construction of commonsense reasoning datasets is expensive, and they are inevitably limited in their scope. A popular approach to UCR is to fine-tune language models with external knowledge (e.g., knowledge graphs), but this usually requires a large number of training examples. In this paper, we propose to transform the downstream multiple choice question answering task into a simpler binary classification task by ranking all candidate answers according to their reasonableness. To this end, for training the model, we convert the knowledge graph triples into reasonable and unreasonable texts. Extensive experimental results show the effectiveness of our approach on various multiple choice question answering benchmarks. Furthermore, compared with existing UCR approaches using KGs, ours is less data hungry.
| Item Type: | Conference or Workshop Item - published (Paper) |
|---|---|
| Date Type: | Publication |
| Status: | Published |
| Schools: | Schools > Computer Science & Informatics |
| Publisher: | ACL |
| ISBN: | 9781959429715 |
| Date of First Compliant Deposit: | 26 May 2023 |
| Date of Acceptance: | 2 May 2023 |
| Last Modified: | 28 Apr 2026 14:27 |
| URI: | https://orca.cardiff.ac.uk/id/eprint/159996 |
Actions (repository staff only)
 |
Edit Item |
Altmetric
Altmetric